{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4OCCQTFIP3PHYSWQE2KRQJLS7I","short_pith_number":"pith:4OCCQTFI","canonical_record":{"source":{"id":"1704.06001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-20T04:13:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"7401f2e14c36932bdf2f4ee760817c7febaa46faedfea59efc97738f13cd82d9","abstract_canon_sha256":"f008776154caf37394b2936293dcf7352ab890b6f496ac692941e8d954c93e47"},"schema_version":"1.0"},"canonical_sha256":"e384284ca87ede7c4ad02695182572fa2829025a2ebc918869675c4564763cca","source":{"kind":"arxiv","id":"1704.06001","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06001","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06001v1","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06001","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"4OCCQTFIP3PH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4OCCQTFIP3PHYSWQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4OCCQTFI","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4OCCQTFIP3PHYSWQE2KRQJLS7I","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-20T04:13:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"7401f2e14c36932bdf2f4ee760817c7febaa46faedfea59efc97738f13cd82d9","abstract_canon_sha256":"f008776154caf37394b2936293dcf7352ab890b6f496ac692941e8d954c93e47"},"schema_version":"1.0"},"canonical_sha256":"e384284ca87ede7c4ad02695182572fa2829025a2ebc918869675c4564763cca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:03.574658Z","signature_b64":"z/xg+On0b5t47M28A5dLdTqsUszelRrb3ZrBTtbAPE/SjjGXlCEqXy4B0y9/Fvdhtdr1koReBLxboqo0Zk9rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e384284ca87ede7c4ad02695182572fa2829025a2ebc918869675c4564763cca","last_reissued_at":"2026-05-18T00:46:03.574115Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:03.574115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06001","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D08XaxDQbdRT9BF9ajqfDjIW87UM582AvoF2aO/qsAbJGE6skZRf1c7K8JrgXQIAt+1InARNhD7F72tR/Q9ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:42:01.829944Z"},"content_sha256":"1bfa2d84861b6c6b841225dc290223ea6c598d6c814897721dc6cc1a33a1d8b8","schema_version":"1.0","event_id":"sha256:1bfa2d84861b6c6b841225dc290223ea6c598d6c814897721dc6cc1a33a1d8b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4OCCQTFIP3PHYSWQE2KRQJLS7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Generation for Convolutional Autoregressive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark A. Hasegawa-Johnson, Mohammad Babaeizadeh, Pooya Khorrami, Prajit Ramachandran, Roy H. Campbell, Shiyu Chang, Thomas S. Huang, Tom Le Paine, Yang Zhang","submitted_at":"2017-04-20T04:13:21Z","abstract_excerpt":"Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a na\\\"{i}ve fashion where redundant computations are unnecessarily repeated. This results in slow generation, making such models infeasible for production environments. In this work, we describe a method to speed up generation in convolutional autoregressive models. The key idea is to cache hidden states to avoid redundant computation. We apply our fast gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06001","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BP3rLoxzufmD6Yw94xUaxxYhPn3h9lqG4Yp7AAFpXIWGsdnXzm4YEz4C8u60wV+cfSKy34YXrCBOlANtb30zDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:42:01.830359Z"},"content_sha256":"dc14cb8bd21df1de96c9c79ef1910ec9401883aed8534e409b04671bc6e9533a","schema_version":"1.0","event_id":"sha256:dc14cb8bd21df1de96c9c79ef1910ec9401883aed8534e409b04671bc6e9533a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/bundle.json","state_url":"https://pith.science/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T11:42:01Z","links":{"resolver":"https://pith.science/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I","bundle":"https://pith.science/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/bundle.json","state":"https://pith.science/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OCCQTFIP3PHYSWQE2KRQJLS7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4OCCQTFIP3PHYSWQE2KRQJLS7I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f008776154caf37394b2936293dcf7352ab890b6f496ac692941e8d954c93e47","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-20T04:13:21Z","title_canon_sha256":"7401f2e14c36932bdf2f4ee760817c7febaa46faedfea59efc97738f13cd82d9"},"schema_version":"1.0","source":{"id":"1704.06001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06001","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06001v1","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06001","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"4OCCQTFIP3PH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4OCCQTFIP3PHYSWQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4OCCQTFI","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:dc14cb8bd21df1de96c9c79ef1910ec9401883aed8534e409b04671bc6e9533a","target":"graph","created_at":"2026-05-18T00:46:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a na\\\"{i}ve fashion where redundant computations are unnecessarily repeated. This results in slow generation, making such models infeasible for production environments. In this work, we describe a method to speed up generation in convolutional autoregressive models. The key idea is to cache hidden states to avoid redundant computation. We apply our fast gener","authors_text":"Mark A. Hasegawa-Johnson, Mohammad Babaeizadeh, Pooya Khorrami, Prajit Ramachandran, Roy H. Campbell, Shiyu Chang, Thomas S. Huang, Tom Le Paine, Yang Zhang","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-20T04:13:21Z","title":"Fast Generation for Convolutional Autoregressive Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06001","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1bfa2d84861b6c6b841225dc290223ea6c598d6c814897721dc6cc1a33a1d8b8","target":"record","created_at":"2026-05-18T00:46:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f008776154caf37394b2936293dcf7352ab890b6f496ac692941e8d954c93e47","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-20T04:13:21Z","title_canon_sha256":"7401f2e14c36932bdf2f4ee760817c7febaa46faedfea59efc97738f13cd82d9"},"schema_version":"1.0","source":{"id":"1704.06001","kind":"arxiv","version":1}},"canonical_sha256":"e384284ca87ede7c4ad02695182572fa2829025a2ebc918869675c4564763cca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e384284ca87ede7c4ad02695182572fa2829025a2ebc918869675c4564763cca","first_computed_at":"2026-05-18T00:46:03.574115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:03.574115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z/xg+On0b5t47M28A5dLdTqsUszelRrb3ZrBTtbAPE/SjjGXlCEqXy4B0y9/Fvdhtdr1koReBLxboqo0Zk9rDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:03.574658Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bfa2d84861b6c6b841225dc290223ea6c598d6c814897721dc6cc1a33a1d8b8","sha256:dc14cb8bd21df1de96c9c79ef1910ec9401883aed8534e409b04671bc6e9533a"],"state_sha256":"65d2de52ad8c025cdcae1130f53d50ec0535e31e2ab214bfd4dca8f2e9cd38ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/YCK8M2t+XaJ+gdrYQlSup/dHrVwHBP9Viiuxa5G6Zcf75nxCVO4OgBkQrWcSgix3vUrLx5ctlZOF2IjfCcBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:42:01.833043Z","bundle_sha256":"6647d454ee3a2c352c2be2eb1533205e519f48b464aaf5141af08326bca08dea"}}